AI agents call fetch_chunk to retrieve information from Wasp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves content from web pages by CSS selector without creating, modifying, deleting, or executing operations. The plain-text fetching is a straightforward read operation with minimal security risk. Severity is low because the worst outcome is accessing publicly or user-accessible web content, with no capability to alter systems or data.
From the tool's definition Tool name 'fetch_chunk' and description 'Fetch the plain-text content of a specific section of a webpage' indicate retrieval without modification.
Attacks that exploit this kind of access
Fetch the plain-text content of a specific section of a webpage by its CSS anchor. It is categorised as a Read tool in the Wasp MCP Server, which means it retrieves data without modifying state.
Register the Wasp MCP server in PolicyLayer and add a rule for fetch_chunk: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Wasp. Nothing to install.
fetch_chunk is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fetch_chunk rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for fetch_chunk. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
fetch_chunk is provided by the Wasp MCP server (sfeeney1897/wasp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →